Sciweavers

10602 search results - page 23 / 2121
» Weakly Useful Sequences
Sort
View
CVPR
2009
IEEE
16 years 9 months ago
Learning Signs from Subtitles: A Weakly Supervised Approach to Sign Language Recognition
This paper introduces a fully-automated, unsupervised method to recognise sign from subtitles. It does this by using data mining to align correspondences in sections of videos. Bas...
Helen Cooper, Richard Bowden
ISMB
1997
15 years 5 months ago
Prediction of Enzyme Classification from Protein Sequence without the Use of Sequence Similarity
1 W’edescribe a novel approach for predicting the function of a protein from its amino-acid sequence. Given features that can be computedfrom the amino-acid sequence in a straigh...
Marie desJardins, Peter D. Karp, Markus Krummenack...
GECCO
2006
Springer
152views Optimization» more  GECCO 2006»
15 years 7 months ago
Strong recombination, weak selection, and mutation
We show that there are unimodal fitness functions and genetic algorithm (GA) parameter settings where the GA, when initialized with a random population, will not move close to the...
Alden H. Wright, J. Neal Richter
ECCC
1998
80views more  ECCC 1998»
15 years 3 months ago
Extracting All the Randomness from a Weakly Random Source
In this paper, we give two explicit constructions of extractors, both of which work for a source of any min-entropy on strings of length n. The rst extracts any constant fraction ...
Salil P. Vadhan
GCB
2004
Springer
139views Biometrics» more  GCB 2004»
15 years 9 months ago
Graph Alignments: A New Concept to Detect Conserved Regions in Protein Active Sites
: We introduce the novel concept of graph alignment, a generalization of graph isomorphism that is motivated by the commonly used multiple sequence alignments. Graph alignments and...
Nils Weskamp, Eyke Hüllermeier, Daniel Kuhn, ...